A text audio push method
An audio and text technology, which is applied in the field of text and audio push, can solve the problems of low recognition accuracy, speech recognition technology does not have segmented recognition and push, and slow text push speed, so as to achieve accurate recognition
Active Publication Date: 2021-08-31
ANHUI SEMXUM INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a text recognition technology to solve the problems that the above speech recognition technology does not have the function of segment recognition and push, which results in a slow push text rate when the network delay is high and the recognition accuracy of traditional speech recognition technology is low. The audio push method has the same segmentation recognition as the heartbeat to push audio and text, and the audio recognition has the advantages of memory function and high recognition accuracy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0021] see figure 1 As shown, a text audio pushing method comprises the following steps:
[0022] S1. Sound processing: the sound is collected by the audio recognition device, and the collected sound and audio data are processed through speech coding technology to generate a sound waveform. The X-axis of the waveform is the time axis in milliseconds, and the Y-axis is the volume axis in milliseconds. in decibels;
[0023] S2. Segment recognition: Set the aud...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a text and audio push method, which belongs to the technical field of audio processing, including S1. sound processing; S2. segment recognition; S3. audio memory; S4. audio recognition according to probability; S5. audio text push. Through the audio recognition equipment, the collected audio is first processed into sound waves, and then the front-end point and the back-end point set by the device are used as the audio recognition interval. When speaking, after each sentence is paused, the audio is recognized as text and then pushed out. Therefore, the audio text received by the user is divided into segments, and the audio text sent by each segment occupies a small capacity, even if the network speed Slower can also be pushed to users quickly, and the segmented text is easy for users to watch.
Description
technical field [0001] The invention relates to the technical field of audio processing, in particular to a method for pushing text and audio. Background technique [0002] Automatic speech recognition technology has developed rapidly in recent years, making it possible for people to communicate and communicate with computers using language. Compared with traditional human-computer interaction methods such as keyboard and mouse, speech provides a more natural human-computer interaction interface. Automatic audio text extraction is based on the core module of the speech recognition system, and the reference text and corresponding speech are A process of forced alignment whose purpose is to convert audio text into text text. As a common preprocessing technology in the field of speech recognition, automatic audio text extraction is widely used in model training, multimedia retrieval, radio and television media, computer-assisted language teaching, etc. In addition, it can also...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/04G10L15/07G10L15/26G10L15/30G10L19/00
Inventor 虞焰兴
Owner ANHUI SEMXUM INFORMATION TECH CO LTD